Correct training provenance, add code link, config with loss-weight keys

README.md

@@ -14,7 +14,7 @@ datasets:
 
 This repository hosts the released weights for **Learning Global Representation from Queries for Vectorized HD Map Construction** (ICML 2026, [arXiv:2510.06969](https://arxiv.org/abs/2510.06969), [project page](https://xr-lee.github.io/mapgr-demo/)).
 
-Training and evaluation code, installation and data preparation are in the GitHub repository (`mapqr/` sub-project).
+Training and evaluation code, installation and data preparation are in the GitHub repository [XR-Lee/MapGR](https://github.com/XR-Lee/MapGR) (`mapqr/` sub-project).
 
 | File | Description |
 |---|---|
@@ -30,11 +30,12 @@ Training and evaluation code, installation and data preparation are in the GitHu
 
 mAP<sub>2</sub> averages Chamfer AP over the {0.5, 1.0, 1.5} m thresholds; mAP<sub>1</sub> averages over {0.2, 0.5, 1.0} m.
 
-This checkpoint was **re-trained with the released code**. It is not the run reported in the paper.
+This checkpoint is not the run reported in the paper.
 
+- It was trained with the research code the GitHub repository was cleaned up from, using the same settings as the released config.
 - Training: 8 GPUs × 4 samples, fp16.
 - The numbers above come from evaluating this exact file with the released `tools/test.py`.
-- Repeated runs of this setting vary by roughly ±0.4 mAP<sub>2</sub>.
+- Other 24-epoch runs of closely related configurations (different seeds, loss weights and query counts) reached 67.2–68.0 mAP<sub>2</sub>.
 
 ```shell
 # inside mapqr/ of the code repository

mapqr_mapgr_nusc_r50_24ep_config.py

@@ -452,7 +452,10 @@ model = dict(
         loss_pts=dict(type='PtsL1Loss', loss_weight=5.0),
         loss_dir=dict(type='PtsDirCosLoss', loss_weight=0.005),
         loss_seg=dict(type='SimpleLoss', pos_weight=4.0, loss_weight=1.0),
-        loss_pv_seg=dict(type='SimpleLoss', pos_weight=1.0, loss_weight=2.0)),
+        loss_pv_seg=dict(type='SimpleLoss', pos_weight=1.0, loss_weight=2.0),
+        aux_loss_weights=[0.05, 0.05, 1.0, 1.0, 1.0],
+        aux_loss_weights_one2many=[1.0, 1.0, 1.0, 1.0, 1.0],
+        global_map_loss_weights=[1.0, 1.0, 0.0, 0.0, 0.0, 0.0]),
     train_cfg=dict(
         pts=dict(
             grid_size=[512, 512, 1],